Journal
DOSE-RESPONSE
Volume 20, Issue 1, Pages -Publisher
SAGE PUBLICATIONS INC
DOI: 10.1177/15593258221082896
Keywords
COVID-19; segmentation algorithms; ultra-low dose; deep learning; artificial intelligence
Funding
- Italian Ministry of Health for the Ricerca Corrente project
- POR CAMPANIA FESR
Ask authors/readers for more resources
A reliable diagnosis and accurate monitoring are crucial for COVID-19 treatment and prevention. Chest CT is considered a crucial diagnostic imaging technique for assessing viral pneumonia injuries, and automated lung segmentation methods help speed up the diagnosis. Ultra-low dose chest CT protocols have been implemented to reduce radiation burden, but existing AI technologies have not been validated for use with these protocols. This study compares the results of four AI tools on datasets acquired with different protocols, finding high comparability between CD-CT and ULD-CT data.
A reliable diagnosis and accurate monitoring are pivotal steps for treatment and prevention of COVID-19. Chest computed tomography (CT) has been considered a crucial diagnostic imaging technique for the injury assessment of the viral pneumonia. Furthermore, the automatization of the segmentation methods for lung alterations helps to speed up the diagnosis and lighten radiologists' workload. Considering the assiduous pathology monitoring, ultra-low dose (ULD) chest CT protocols have been implemented to drastically reduce the radiation burden. Unfortunately, the available AI technologies have not been trained on ULD-CT data and validated and their applicability deserves careful evaluation. Therefore, this work aims to compare the results of available AI tools (BCUnet, CORADS AI, NVIDIA CLARA Train SDK and CT Pneumonia Analysis) on a dataset of 73 CT examinations acquired both with conventional dose (CD) and ULD protocols. COVID-19 volume percentage, resulting from each tool, was statistically compared. This study demonstrated high comparability of the results on CD-CT and ULD-CT data among the four AI tools, with high correlation between the results obtained on both protocols (R > .68, P < .001, for all AI tools).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available